Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2995 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0892. Min Range: -3.0892

Max Act: 3.0892. Min Act: -0.0000

Data Index: 832053 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.3828. Min Act: -0.0000

Data Index: 860991 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.4606. Min Act: -0.0000

Data Index: 284484 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.2725. Min Act: -0.0000

Data Index: 243745 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.3933. Min Act: -0.0001

Data Index: 387631 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.2868. Min Act: -0.0000

Data Index: 939843 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.0776. Min Act: -0.0000

Data Index: 1043011 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.2448. Min Act: -0.0000

Data Index: 248176 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.1463. Min Act: -0.0000

Data Index: 32756 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.0159. Min Act: -0.0000

Data Index: 653379 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.2033. Min Act: -0.0000

Data Index: 65051 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.0694. Min Act: -0.0000

Data Index: 1081987 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.1607. Min Act: -0.0000

Data Index: 904123 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.0305. Min Act: -0.0000

Data Index: 705174 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.1442. Min Act: -0.0000

Data Index: 1108013 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.1476. Min Act: -0.0000

Data Index: 105678 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.1158. Min Act: -0.0000

Data Index: 233827 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.1311. Min Act: -0.0000

Data Index: 343883 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 3.0892. Min Range: -3.0892

Max Act: 1.9822. Min Act: -0.0001

Data Index: 1115116 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 3.0892. Min Range: -3.0892

Max Act: 2.0148. Min Act: -0.0000

Data Index: 249419 (C4 (Web Text))

Max Activating Token Index: 816